sqoop-CSDN博客

本文链接：https://blog.csdn.net/qq_43827516/article/details/109458734

同步策略
数据同步策略的类型包括：全量表、增量表、新增及变化表、特殊表
全量表：存储完整的数据。
增量表：存储新增加的数据。
新增及变化表：存储新增加的数据和变化的数据。
特殊表：只需要存储一次。
脚本编写
1）在/home/ss/bin目录下创建
[atguigu@hadoop102 bin]$ vim mysql_to_hdfs.sh
添加如下内容：

#! /bin/bash

sqoop=/opt/module/sqoop/bin/sqoop

if [ -n "$2" ] ;then
    do_date=$2
else
    do_date=`date -d '-1 day' +%F`
fi

import_data(){
$sqoop import \
--connect jdbc:mysql://hadoop102:3306/gmall \
--username root \
--password 000000 \
--target-dir /origin_data/gmall/db/$1/$do_date \
--delete-target-dir \
--query "$2 and  \$CONDITIONS" \
--num-mappers 1 \
--fields-terminated-by '\t' \
--compress \
--compression-codec lzop \
--null-string '\\N' \
--null-non-string '\\N'

hadoop jar /opt/module/hadoop-3.1.3/share/hadoop/common/hadoop-lzo-0.4.20.jar com.hadoop.compression.lzo.DistributedLzoIndexer /origin_data/gmall/db/$1/$do_date
}

import_order_info(){
  import_data order_info "select
                            id, 
                            final_total_amount, 
                            order_status, 
                            user_id, 
                            out_trade_no, 
                            create_time, 
                            operate_time,
                            province_id,
                            benefit_reduce_amount,
                            original_total_amount,
                            feight_fee      
                        from order_info
                        where (date_format(create_time,'%Y-%m-%d')='$do_date' 
                        or date_format(operate_time,'%Y-%m-%d')='$do_date')"
}

import_coupon_use(){
  import_data coupon_use "select
                          id,
                          coupon_id,
                          user_id,
                          order_id,
                          coupon_status,
                          get_time,
                          using_time,
                          used_time
                        from coupon_use
                        where (date_format(get_time,'%Y-%m-%d')='$do_date'
                        or date_format(using_time,'%Y-%m-%d')='$do_date'
                        or date_format(used_time,'%Y-%m-%d')='$do_date')"
}

import_order_status_log(){
  import_data order_status_log "select
                                  id,
                                  order_id,
                                  order_status,
                                  operate_time
                                from order_status_log
                                where date_format(operate_time,'%Y-%m-%d')='$do_date'"
}

import_activity_order(){
  import_data activity_order "select
                                id,
                                activity_id,
                                order_id,
                                create_time
                              from activity_order
                              where date_format(create_time,'%Y-%m-%d')='$do_date'"
}

import_user_info(){
  import_data "user_info" "select 
                            id,
                            name,
                            birthday,
                            gender,
                            email,
                            user_level, 
                            create_time,
                            operate_time
                          from user_info 
                          where (DATE_FORMAT(create_time,'%Y-%m-%d')='$do_date' 
                          or DATE_FORMAT(operate_time,'%Y-%m-%d')='$do_date')"
}

import_order_detail(){
  import_data order_detail "select 
                              od.id,
                              order_id, 
                              user_id, 
                              sku_id,
                              sku_name,
                              order_price,
                              sku_num, 
                              od.create_time,
                              source_type,
                              source_id  
                            from order_detail od
                            join order_info oi
                            on od.order_id=oi.id
                            where DATE_FORMAT(od.create_time,'%Y-%m-%d')='$do_date'"
}

import_payment_info(){
  import_data "payment_info"  "select 
                                id,  
                                out_trade_no, 
                                order_id, 
                                user_id, 
                                alipay_trade_no, 
                                total_amount,  
                                subject, 
                                payment_type, 
                                payment_time 
                              from payment_info 
                              where DATE_FORMAT(payment_time,'%Y-%m-%d')='$do_date'"
}

import_comment_info(){
  import_data comment_info "select
                              id,
                              user_id,
                              sku_id,
                              spu_id,
                              order_id,
                              appraise,
                              comment_txt,
                              create_time
                            from comment_info
                            where date_format(create_time,'%Y-%m-%d')='$do_date'"
}

import_order_refund_info(){
  import_data order_refund_info "select
                                id,
                                user_id,
                                order_id,
                                sku_id,
                                refund_type,
                                refund_num,
                                refund_amount,
                                refund_reason_type,
                                create_time
                              from order_refund_info
                              where date_format(create_time,'%Y-%m-%d')='$do_date'"
}

import_sku_info(){
  import_data sku_info "select 
                          id,
                          spu_id,
                          price,
                          sku_name,
                          sku_desc,
                          weight,
                          tm_id,
                          category3_id,
                          create_time
                        from sku_info where 1=1"
}

import_base_category1(){
  import_data "base_category1" "select 
                                  id,
                                  name 
                                from base_category1 where 1=1"
}

import_base_category2(){
  import_data "base_category2" "select
                                  id,
                                  name,
                                  category1_id 
                                from base_category2 where 1=1"
}

import_base_category3(){
  import_data "base_category3" "select
                                  id,
                                  name,
                                  category2_id
                                from base_category3 where 1=1"
}

import_base_province(){
  import_data base_province "select
                              id,
                              name,
                              region_id,
                              area_code,
                              iso_code
                            from base_province
                            where 1=1"
}

import_base_region(){
  import_data base_region "select
                              id,
                              region_name
                            from base_region
                            where 1=1"
}

import_base_trademark(){
  import_data base_trademark "select
                                tm_id,
                                tm_name
                              from base_trademark
                              where 1=1"
}

import_spu_info(){
  import_data spu_info "select
                            id,
                            spu_name,
                            category3_id,
                            tm_id
                          from spu_info
                          where 1=1"
}

import_favor_info(){
  import_data favor_info "select
                          id,
                          user_id,
                          sku_id,
                          spu_id,
                          is_cancel,
                          create_time,
                          cancel_time
                        from favor_info
                        where 1=1"
}

import_cart_info(){
  import_data cart_info "select
                        id,
                        user_id,
                        sku_id,
                        cart_price,
                        sku_num,
                        sku_name,
                        create_time,
                        operate_time,
                        is_ordered,
                        order_time,
                        source_type,
                        source_id
                      from cart_info
                      where 1=1"
}

import_coupon_info(){
  import_data coupon_info "select
                          id,
                          coupon_name,
                          coupon_type,
                          condition_amount,
                          condition_num,
                          activity_id,
                          benefit_amount,
                          benefit_discount,
                          create_time,
                          range_type,
                          spu_id,
                          tm_id,
                          category3_id,
                          limit_num,
                          operate_time,
                          expire_time
                        from coupon_info
                        where 1=1"
}

import_activity_info(){
  import_data activity_info "select
                              id,
                              activity_name,
                              activity_type,
                              start_time,
                              end_time,
                              create_time
                            from activity_info
                            where 1=1"
}

import_activity_rule(){
    import_data activity_rule "select
                                    id,
                                    activity_id,
                                    condition_amount,
                                    condition_num,
                                    benefit_amount,
                                    benefit_discount,
                                    benefit_level
                                from activity_rule
                                where 1=1"
}

import_base_dic(){
    import_data base_dic "select
                            dic_code,
                            dic_name,
                            parent_code,
                            create_time,
                            operate_time
                          from base_dic
                          where 1=1"
}

case $1 in
  "order_info")
     import_order_info
;;
  "base_category1")
     import_base_category1
;;
  "base_category2")
     import_base_category2
;;
  "base_category3")
     import_base_category3
;;
  "order_detail")
     import_order_detail
;;
  "sku_info")
     import_sku_info
;;
  "user_info")
     import_user_info
;;
  "payment_info")
     import_payment_info
;;
  "base_province")
     import_base_province
;;
  "base_region")
     import_base_region
;;
  "base_trademark")
     import_base_trademark
;;
  "activity_info")
      import_activity_info
;;
  "activity_order")
      import_activity_order
;;
  "cart_info")
      import_cart_info
;;
  "comment_info")
      import_comment_info
;;
  "coupon_info")
      import_coupon_info
;;
  "coupon_use")
      import_coupon_use
;;
  "favor_info")
      import_favor_info
;;
  "order_refund_info")
      import_order_refund_info
;;
  "order_status_log")
      import_order_status_log
;;
  "spu_info")
      import_spu_info
;;
  "activity_rule")
      import_activity_rule
;;
  "base_dic")
      import_base_dic
;;

"first")
   import_base_category1
   import_base_category2
   import_base_category3
   import_order_info
   import_order_detail
   import_sku_info
   import_user_info
   import_payment_info
   import_base_province
   import_base_region
   import_base_trademark
   import_activity_info
   import_activity_order
   import_cart_info
   import_comment_info
   import_coupon_use
   import_coupon_info
   import_favor_info
   import_order_refund_info
   import_order_status_log
   import_spu_info
   import_activity_rule
   import_base_dic
;;
"all")
   import_base_category1
   import_base_category2
   import_base_category3
   import_order_info
   import_order_detail
   import_sku_info
   import_user_info
   import_payment_info
   import_base_trademark
   import_activity_info
   import_activity_order
   import_cart_info
   import_comment_info
   import_coupon_use
   import_coupon_info
   import_favor_info
   import_order_refund_info
   import_order_status_log
   import_spu_info
   import_activity_rule
   import_base_dic
;;
esac

说明1：
[ -n 变量值 ] 判断变量的值，是否为空
– 变量的值，非空，返回true
– 变量的值，为空，返回false
说明2：
查看date命令的使用，[ss@hadoop102 ~]$ date --help
2）修改脚本权限
[ss@hadoop102 bin]$ chmod 777 mysql_to_hdfs.sh
3）初次导入
[ss@hadoop102 bin]$ mysql_to_hdfs.sh first 2020-06-14
4）每日导入
[ss@hadoop102 bin]$ mysql_to_hdfs.sh all 2020-06-15

项目经验
Hive中的Null在底层是以“\N”来存储，而MySQL中的Null在底层就是Null，为了保证数据两端的一致性。在导出数据时采用–input-null-string和–input-null-non-string两个参数。导入数据时采用–null-string和–null-non-string。

shell脚本

[atguigu@hadoop102 bin]$ vim mysql_to_hdfs.sh
#! /bin/bash

sqoop=/opt/module/sqoop/bin/sqoop

if [ -n "$2" ] ;then
    do_date=$2
else
    do_date=`date -d '-1 day' +%F`
fi

import_data(){
$sqoop import \
--connect jdbc:mysql://hadoop102:3306/gmail \
--username root \
--password 123456 \
--target-dir /origin_data/gmail/db/$1/$do_date \
--delete-target-dir \
--query "$2 and  \$CONDITIONS" \
--num-mappers 1 \
--fields-terminated-by '\t' \
--compress \
--compression-codec lzop \
--null-string '\\N' \
--null-non-string '\\N'

hadoop jar /opt/module/hadoop/share/hadoop/common/hadoop-lzo-0.4.20.jar com.hadoop.compression.lzo.DistributedLzoIndexer /origin_data/gmail/db/$1/$do_date
}

import_order_status_log(){
  import_data order_status_log "select
                                  id,
                                  order_id,
                                  order_status,
                                  operate_time
                                from order_status_log
                                where date_format(operate_time,'%Y-%m-%d')='$do_date'"
}
case $1 in
  "order_info")
     import_order_info
;;
 "order_status_log")
      import_order_status_log
;;
"first")
全量表、特殊表、新增表、新增+变化表
;;
"second")
全量表、新增表、新增+变化表
;;
esac

脚本说明

date -d '-1 day' （当前日期的前一天）
2020年 07月 12日 星期日 14:49:59 CST
date -d '-1 day' +%F（格式化）
2020-07-12
--fields-terminated-by '\t' ，需与hive建表时一致
date_format(create_time,'%Y-%m-%d')，日期格式化为yyyy-MM-dd

--compression-codec lzop \ 指定为lzop的格式，必须要对上传的LZO文件建索引
hadoop jar /opt/module/hadoop/share/hadoop/common/hadoop-lzo-0.4.20.jar com.hadoop.compression.lzo.DistributedLzoIndexer /origin_data/gmail/db/$1/$do_date